← Back to community benchmarks

Qwen2.5-7B-Instruct

M5 (10c) · 16 GB · 4bit · 2026-05-18
Performance
1k
tokens
790.4
PP tok/s
30.6
TG tok/s
1296
TTFT (ms)
4.5
Peak mem (GB)
Hardware
Chip M5 (10c)
Memory 16 GB
GPU Cores 10
Software
oMLX v0.3.9.dev2
macOS macOS 26.5
Context 1,024
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 790.4 30.6 4.5 GB current
4k 808.7 28.8 5.0 GB view
Batching Results
Batch Size TG tok/s Speedup
30.6 1.00×
60.6 1.98×
74.6 2.44×